Complex-valued convolutional neural networks for real-valued image classification

In this paper, complex-valued convolutional neural networks are presented, by giving the full deduction of the gradient descent algorithm for training this type of networks. The performances of convolutional neural networks in the real-valued domain for image classification gave rise to the idea of extending them to the complex-valued domain, also. Real-valued image classification experiments done using the MNIST and CIFAR-10 datasets have shown an improvement in performance of complex-valued convolutional neural networks over their real-valued counterparts.